This study explores the potential of using acoustic features of segmental speech sounds to detect deepfake audio. These features are highly interpretable because of their close relationship with human articulatory processes and are expected to be more difficult for deepfake models to replicate. The results demonstrate that certain segmental features commonly used in forensic voice comparison (FVC) are effective in identifying deep-fakes, whereas some global features provide little value. These findings underscore the need to approach audio deepfake detection using methods that are distinct from those employed in traditional FVC, and offer a new perspective on leveraging segmental features for this purpose. In addition, the present study proposes a speaker-specific framework for deepfake detection, which differs fundamentally from the speaker-independent systems that dominate current benchmarks. While speaker-independent frameworks aim at broad generalization, the speaker-specific approach offers advantages in forensic contexts where case-by-case interpretability and sensitivity to individual phonetic realization are essential.

Advances in multimodal machine learning have made text-to-image (T2I) models increasingly accessible and popular. However, T2I models introduce risks such as the generation of non-consensual depictions of identifiable individuals, otherwise known as deepfakes. This paper presents an empirical study exploring the accessibility of deepfake model variants online. Through a metadata analysis of thousands of publicly downloadable model variants on two popular repositories, Hugging Face and Civitai, we demonstrate a huge rise in easily accessible deepfake models. Almost 35,000 examples of publicly downloadable deepfake model variants are identified, primarily hosted on Civitai. These deepfake models have been downloaded almost 15 million times since November 2022, with the models targeting a range of individuals from global celebrities to Instagram users with under 10,000 followers. Both Stable Diffusion and Flux models are used for the creation of deepfake models, with 96% of these targeting women and many signalling intent to generate non-consensual intimate imagery (NCII). Deepfake model variants are often created via the parameter-efficient fine-tuning technique known as low rank adaptation (LoRA), requiring as few as 20 images, 24GB VRAM, and 15 minutes of time, making this process widely accessible via consumer-grade computers. Despite these models violating the Terms of Service of hosting platforms, and regulation seeking to prevent dissemination, these results emphasise the pressing need for greater action to be taken against the creation of deepfakes and NCII.

Deepfakes, malicious visual contents created by generative models, pose an increasingly harmful threat to society. To proactively mitigate deepfake damages, recent studies have employed adversarial perturbation to disrupt deepfake model outputs. However, previous approaches primarily focus on generating distorted outputs based on only predetermined target attributes, leading to a lack of robustness in real-world scenarios where target attributes are unknown. Additionally, the transferability of perturbations between two prominent generative models, Generative Adversarial Networks (GANs) and Diffusion Models, remains unexplored. In this paper, we emphasize the importance of target attribute-transferability and model-transferability for achieving robust deepfake disruption. To address this challenge, we propose a simple yet effective disruption method called Latent Ensemble ATtack (LEAT), which attacks the independent latent encoding process. By disrupting the latent encoding process, it generates distorted output images in subsequent generation processes, regardless of the given target attributes. This target attribute-agnostic attack ensures robust disruption even when the target attributes are unknown. Additionally, we introduce a Normalized Gradient Ensemble strategy that effectively aggregates gradients for iterative gradient attacks, enabling simultaneous attacks on various types of deepfake models, involving both GAN-based and Diffusion-based models. Moreover, we demonstrate the insufficiency of evaluating disruption quality solely based on pixel-level differences. As a result, we propose an alternative protocol for comprehensively evaluating the success of defense. Extensive experiments confirm the efficacy of our method in disrupting deepfakes in real-world scenarios, reporting a higher defense success rate compared to previous methods.

Adversarial example is a rising way of protecting facial privacy security from deepfake modification. To prevent massive facial images from being illegally modified by various deepfake models, it is essential to design a universal deepfake disruptor. However, existing works treat deepfake disruption as an End-to-End process, ignoring the functional difference between feature extraction and image reconstruction, which makes it difficult to generate a cross-model universal disruptor. In this work, we propose a novel Feature-Output ensemble UNiversal Disruptor (FOUND) against deepfake networks, which explores a new opinion that considers attacking feature extractors as the more critical and general task in deepfake disruption. We conduct an effective two-stage disruption process. We first disrupt multi-model feature extractors through multi-feature aggregation and individual-feature maintenance, and then develop a gradient-ensemble algorithm to enhance the disruption effect by simplifying the complex optimization problem of disrupting multiple End-to-End models. Extensive experiments demonstrate that FOUND can significantly boost the disruption effect against ensemble deepfake benchmark models. Besides, our method can fast obtain a cross-attribute, cross-image, and cross-model universal deepfake disruptor with only a few training images, surpassing state-of-the-art universal disruptors in both success rate and efficiency.

New research from New York University adds to the growing indications that we may soon have to take the deepfake equivalent of a'drunk test' in order to authenticate ourselves, before commencing a sensitive video call – such as a work-related videoconference, or any other sensitive scenario that may attract fraudsters using real-time deepfake streaming software. Some of the active and passive challenges applied to video-call scenarios in GOTCHA. The user must comply with and pass the challenges, while additional'passive' methods (such as attempting to overload a potential deepfake system) are used over which the participant has no influence. The proposed system is titled GOTCHA – a tribute to the CAPTCHA systems that have become an increasing obstacle to web-browsing over the last 10-15 years, wherein automated systems require the user to perform tasks that machines are bad at, such as identifying animals or deciphering garbled text (and, ironically, these challenges often turn the user into a free AMT-style outsourced annotator). In essence, GOTCHA extends the August 2022 DF-Captcha paper from Ben-Gurion University, which was the first to propose making the person at the other end of the call jump through a few visually semantic hoops in order to prove their authenticity.

Google has quietly banned deepfake projects on its Colaboratory (Colab) service, putting an end to the large-scale utilization of the platform's resources for this purpose. Colab is an online computing resource that allows researchers to run Python code directly through the browser while using free computing resources, including GPUs, to power their projects. Due to the multi-core nature of GPUs, Colab is ideal for training machine learning projects like deepfake models or for performing data analysis. Deepfakes can be trained to swap faces on video clips, adding realistic facial expressions to make the result appear genuine, although it's fake. They have been used for spreading fake news, creating revenge porn, or for fun.

Malicious application of deepfakes (i.e., technologies can generate target faces or face attributes) has posed a huge threat to our society. The fake multimedia content generated by deepfake models can harm the reputation and even threaten the property of the person who has been impersonated. Fortunately, the adversarial watermark could be used for combating deepfake models, leading them to generate distorted images. The existing methods require an individual training process for every facial image, to generate the adversarial watermark against a specific deepfake model, which are extremely inefficient. To address this problem, we propose a universal adversarial attack method on deepfake models, to generate a Cross-Model Universal Adversarial Watermark (CMUA-Watermark) that can protect thousands of facial images from multiple deepfake models. Specifically, we first propose a cross-model universal attack pipeline by attacking multiple deepfake models and combining gradients from these models iteratively. Then we introduce a batch-based method to alleviate the conflict of adversarial watermarks generated by different facial images. Finally, we design a more reasonable and comprehensive evaluation method for evaluating the effectiveness of the adversarial watermark. Experimental results demonstrate that the proposed CMUA-Watermark can effectively distort the fake facial images generated by deepfake models and successfully protect facial images from deepfakes in real scenes.